public DefaultHtmlEncoder(CodePointFilter filter)
{
_allowedCharsBitmap = filter.GetAllowedCharsBitmap();
// Forbid codepoints which aren't mapped to characters or which are otherwise always disallowed
// (includes categories Cc, Cs, Co, Cn, Zs [except U+0020 SPACE], Zl, Zp)
_allowedCharsBitmap.ForbidUndefinedCharacters();
ForbidHtmlCharacters(_allowedCharsBitmap);
}
/// <summary>
/// Instantiates the filter by cloning the allow list of another <see cref="ICodePointFilter"/>.
/// </summary>
public CodePointFilter(ICodePointFilter other)
{
CodePointFilter otherAsCodePointFilter = other as CodePointFilter;
if (otherAsCodePointFilter != null)
{
_allowedCharsBitmap = otherAsCodePointFilter.GetAllowedCharsBitmap();
}
else
{
_allowedCharsBitmap = AllowedCharsBitmap.CreateNew();
AllowFilter(other);
}
}
public DefaultJavaScriptEncoder(CodePointFilter filter)
{
_allowedCharsBitmap = filter.GetAllowedCharsBitmap();
// Forbid codepoints which aren't mapped to characters or which are otherwise always disallowed
// (includes categories Cc, Cs, Co, Cn, Zs [except U+0020 SPACE], Zl, Zp)
_allowedCharsBitmap.ForbidUndefinedCharacters();
// Forbid characters that are special in HTML.
// Even though this is a not HTML encoder,
// it's unfortunately common for developers to
// forget to HTML-encode a string once it has been JS-encoded,
// so this offers extra protection.
DefaultHtmlEncoder.ForbidHtmlCharacters(_allowedCharsBitmap);
_allowedCharsBitmap.ForbidCharacter('\\');
_allowedCharsBitmap.ForbidCharacter('/');
}
/// <summary>
/// Instantiates an encoder using a custom allow list of characters.
/// </summary>
protected UnicodeEncoderBase(CodePointFilter filter, int maxOutputCharsPerInputChar)
{
_maxOutputCharsPerInputChar = maxOutputCharsPerInputChar;
_allowedCharsBitmap = filter.GetAllowedCharsBitmap();
// Forbid characters that are special in HTML.
// Even though this is a common encoder used by everybody (including URL
// and JavaScript strings), it's unfortunately common for developers to
// forget to HTML-encode a string once it has been URL-encoded or
// JavaScript string-escaped, so this offers extra protection.
ForbidCharacter('<');
ForbidCharacter('>');
ForbidCharacter('&');
ForbidCharacter('\''); // can be used to escape attributes
ForbidCharacter('\"'); // can be used to escape attributes
ForbidCharacter('+'); // technically not HTML-specific, but can be used to perform UTF7-based attacks
// Forbid codepoints which aren't mapped to characters or which are otherwise always disallowed
// (includes categories Cc, Cs, Co, Cn, Zs [except U+0020 SPACE], Zl, Zp)
_allowedCharsBitmap.ForbidUndefinedCharacters();
}
public DefaultUrlEncoder(CodePointFilter filter)
{
_allowedCharsBitmap = filter.GetAllowedCharsBitmap();
// Forbid codepoints which aren't mapped to characters or which are otherwise always disallowed
// (includes categories Cc, Cs, Co, Cn, Zs [except U+0020 SPACE], Zl, Zp)
_allowedCharsBitmap.ForbidUndefinedCharacters();
// Forbid characters that are special in HTML.
// Even though this is a not HTML encoder,
// it's unfortunately common for developers to
// forget to HTML-encode a string once it has been URL-encoded,
// so this offers extra protection.
DefaultHtmlEncoder.ForbidHtmlCharacters(_allowedCharsBitmap);
// Per RFC 3987, Sec. 2.2, we want encodings that are safe for
// four particular components: 'isegment', 'ipath-noscheme',
// 'iquery', and 'ifragment'. The relevant definitions are below.
//
// ipath-noscheme = isegment-nz-nc *( "/" isegment )
//
// isegment = *ipchar
//
// isegment-nz-nc = 1*( iunreserved / pct-encoded / sub-delims
// / "@" )
// ; non-zero-length segment without any colon ":"
//
// ipchar = iunreserved / pct-encoded / sub-delims / ":"
// / "@"
//
// iquery = *( ipchar / iprivate / "/" / "?" )
//
// ifragment = *( ipchar / "/" / "?" )
//
// iunreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" / ucschar
//
// ucschar = %xA0-D7FF / %xF900-FDCF / %xFDF0-FFEF
// / %x10000-1FFFD / %x20000-2FFFD / %x30000-3FFFD
// / %x40000-4FFFD / %x50000-5FFFD / %x60000-6FFFD
// / %x70000-7FFFD / %x80000-8FFFD / %x90000-9FFFD
// / %xA0000-AFFFD / %xB0000-BFFFD / %xC0000-CFFFD
// / %xD0000-DFFFD / %xE1000-EFFFD
//
// pct-encoded = "%" HEXDIG HEXDIG
//
// sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
// / "*" / "+" / "," / ";" / "="
//
// The only common characters between these four components are the
// intersection of 'isegment-nz-nc' and 'ipchar', which is really
// just 'isegment-nz-nc' (colons forbidden).
//
// From this list, the base encoder already forbids "&", "'", "+",
// and we'll additionally forbid "=" since it has special meaning
// in x-www-form-urlencoded representations.
//
// This means that the full list of allowed characters from the
// Basic Latin set is:
// ALPHA / DIGIT / "-" / "." / "_" / "~" / "!" / "$" / "(" / ")" / "*" / "," / ";" / "@"
const string forbiddenChars = @" #%/:=?[\]^`{|}"; // chars from Basic Latin which aren't already disallowed by the base encoder
foreach (char c in forbiddenChars)
{
_allowedCharsBitmap.ForbidCharacter(c);
}
// Specials (U+FFF0 .. U+FFFF) are forbidden by the definition of 'ucschar' above
for (int i = 0; i < 16; i++)
{
_allowedCharsBitmap.ForbidCharacter((char)(0xFFF0 | i));
}
// Supplementary characters are forbidden anyway by the base encoder //TODO: make sure it's true after the changes
}